Havuz

Self-evolving AI workspace — it rewrites its own UI, tools, skills and plugins while it runs, live on screen. Local-first, one Go binary, no

A harness optimized to smaller LLMs

TaiyiForge, Claude, Codex, Cursor ve OpenCode için AI destekli yazılım geliştirmeyi aşamalı ve denetlenebilir bir workflow'a dönüştüren TypeScript tabanlı bir araçtır.

Neden yükseliyor · 115 günlük bir repo için 886 yıldız dikkat çekici; AI coding agent'ları için tekrarlanabilir workflow ve kontrol ihtiyacına denk geliyor olabilir. Ancak yıldızların nedenini doğrulayan ek veri yok ve son 28 günde commit ile farklı yazar sayısı sıfır; bu nedenle ilginin güncel geliştirme faaliyetiyle desteklendiği söylenemez.

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi

A production-oriented Go framework for distributed applications with explicit lifecycle, transport, governance, observability, and contract-

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

Open-source app builder engine — intent to working app

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, a

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7

Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, contr

The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.

说出你的需要，让应用在身边的屏幕上诞生——云端编码 Agent 当场生成 Web 应用，投到电视或投影上，并用语音继续操作。

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

Turn an OpenAPI file or a recorded website into a curated, tested MCP server; your agent designs the tools.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven,

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

A coding agent harness built specifically for Motif-3

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden

Ontology-driven WorkBuddy skill for requirements discovery, domain modeling, and app generation | WorkBuddy 需求探索、本体建模与领域应用生成器

AI-powered QA agent for VS Code. Analyzes code changes, generates test plans, runs real browser tests, and delivers evidence-backed merge ve

An open-source build system that compiles your specs and architecture into working code.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

AI-powered desktop app for migrating Python projects to Rust. Supports multiple LLM providers (OpenAI, Anthropic, Ollama), includes 300+ lib

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Component contracts: one machine-readable source of truth that generates both a React library and a Figma library, proves they match with a

Open-source OpenAPI mock server with cloud hosting and local modes for development, testing, and CI. Generates realistic API responses from

A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and deliver

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

Create and run Phoenix projects on localhost with nothing installed but Docker, and keep what you learn about the Elixir ecosystem as cartr

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

A Nix library for parsing, inspecting, and transforming AST

The polyglot binding generator behind the xberg.io ecosystem: language-native bindings, packages, docs and e2e tests from one alef.toml.

Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, a

Agent 工坊（Agent Workshop）：给它一个 PRD、一个需求点子、或一个可落地的 Agent 方向，它推导出架构方案、组件选型与代码骨架，直到一个能在真实环境运行的产品。

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

The same HTTP API in 10 languages at 3 sizes, 30 implementations. Token cost for LLM agents, plus cold start, latency, throughput, CPU and m

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением

Domain-agnostic multi-agent software design and evolution harness

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compati

SQL as a first-class language: formatting, linting, security auditing and pre-commit hooks for your .sql files, plus type-safe code generati

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-

不要偷偷上传代码啊魂淡！

LinuxMint Scripter es una aplicación web de una sola página que permite crear scripts de Bash o Python listos para usar en Linux Mint 22.3.

Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out. 12 role subagents, 9 gated p

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation,